Instructions to use xinyuema/llm-course-hw2-ppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xinyuema/llm-course-hw2-ppo with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xinyuema/llm-course-hw2-ppo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xinyuema/llm-course-hw2-ppo")
model = AutoModelForCausalLM.from_pretrained("xinyuema/llm-course-hw2-ppo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xinyuema/llm-course-hw2-ppo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xinyuema/llm-course-hw2-ppo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xinyuema/llm-course-hw2-ppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xinyuema/llm-course-hw2-ppo

SGLang

How to use xinyuema/llm-course-hw2-ppo with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "xinyuema/llm-course-hw2-ppo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xinyuema/llm-course-hw2-ppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "xinyuema/llm-course-hw2-ppo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xinyuema/llm-course-hw2-ppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xinyuema/llm-course-hw2-ppo with Docker Model Runner:
```
docker model run hf.co/xinyuema/llm-course-hw2-ppo
```

Model Card for Model ID

The alignment based on HuggingFaceTB/SmolLM-135M-Instruct model with a pre-trained reward model with trained by ourselves on the Human-Like-DPO-Dataset using PPO method.

Model Details

On this stage we trained a policy model which was initialized from the based model HuggingFaceTB/SmolLM-135M-Instruct an a value model trained at the last block.

Examples

======== BEFORE TUNING ========

user

What's your morning routine like?

assistant

I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine that I've developed based on various studies and research:

**Morning Routine (10-15 minutes)**

1. **Hydrate**: Drink a full glass of water or a herbal tea (e.g., chamomile, peppermint) to start the day.
2. **Eat a nutritious breakfast**: Prepare a healthy breakfast, such as oatmeal with fruit, scrambled eggs with spinach, or Greek yogurt with berries.
3. **Get some morning sunlight**: Spend 10-15 minutes outside in natural light to help regulate your circadian rhythms.
4. **Take a few deep breaths**: Inhale for 1-2 minutes, hold for 2-3 minutes, and exhale for 2-3 minutes.
5. **Stretch or move**: Engage in some light stretching or movement to get your blood flowing and your muscles moving.

**Morning Routine (15-30 minutes)**

Get some morning sunlight: Spend 10-1

======== AFTER TUNING ========

user

What's your morning routine like?

assistant

user What's your morning routine like? assistant What a great question! I'd be happy to share my morning routine with you. Here's a sample morning routine that I've developed over the years:

Morning Routine (7:00 AM - 10:00 AM)

Breakfast